The use of artificial neural networks in analysing the nutritional ecology of Chrysomya megacephala (F.) (Diptera: Calliphoridae), compared with a statistical model

Artificial neural networks (ANNs) have been widely applied to the resolution of complex biological problems. An important feature of neural models is that their implementation is not precluded by the theoretical distribution shape of the data used. Frequently, the performance of ANNs over linear or non-linear regression-based statistical methods is deemed to be significantly superior if suitable sample sizes are provided, especially in multidimensional and non-linear processes. The current work was aimed at utilising three well-known neural network methods in order to evaluate whether these models would be able to provide more accurate outcomes in relation to a conventional regression method in pupal weight predictions of Chrysomya megacephala, a species of blowfly (Diptera: Calliphoridae), using larval density (i.e. the initial number of larvae), amount of available food and pupal size as input data. It was possible to notice that the neural networks yielded more accurate performances in comparison with the statistical model (multiple regression). Assessing the three types of networks utilised (Multi-layer Perceptron, Radial Basis Function and Generalised Regression Neural Network), no considerable differences between these models were detected. The superiority of these neural models over a classical statistical method represents an important fact, because more accurate models may clarify several intricate aspects concerning the nutritional ecology of blowflies.

Nitrogen immobilization by Congo grass roots impairs cotton initial growth

In crop-livestock integration systems the presence of both grass roots in the soil and straw on the surface can temporarily immobilize nitrogen. This study examined the persistence of grass residues in the system as well as their effects on cotton response to N when grown after Congo grass (Brachiaria ruziziensis, Syn. Urochloa ruziziensis). Congo grass was grown in pots with soil. Next, cotton was grown in the same pots without residues, with whole plant residues (Congo grass roots and shoots) or root residues (grass roots) and fertilized with N as ammonium nitrate. Congo grass and cotton roots were separated using stable carbon isotope fractioning. Congo grass roots showed higher C/N ratio than shoots, losing 14% of its mass after 45 days and increasing soil N immobilization. The lower N availability resulted in N deficient and shorter cotton plants with lower dry matter yields. Nevertheless, the application of 80 to 120 mg kg-1 of N compensated the immobilization by the soil microorganisms, allowing cotton to show normal growth. When Congo grass is present in the cropping system, the effects of the decaying roots on soil N dynamics and availability are more important than those of the straw left on the soil surface.

Efeito de dois diferentes programas de intervenção sobre parâmetros cinemáticos da marcha e testes de mobilidade em pacientes com doença de parkinson

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Análise e aplicação de métodos de modularização no desenvolvimento do produto

Pós-graduação em Engenharia de Produção - FEG

Pure spinor superstring partition function

Pós-graduação em Física - IFT